Skin Lesions Identification and Analysis with Deep Learning Model Using Transfer Learning

Abstract

Sunlight has beneficial as well as harmful rays. Environmental pollution occurs as a result of the depletion of the ozone layer caused by the damage caused by humans to the environment. As a result of these pollutants, skin diseases can be seen in areas exposed to direct sunlight, such as the head and neck. Early detection of actinic keratosis (akiec), basal cell carcinoma (bcc), bening keratosis (bkl), dermafibroma (df), melanoma (mel), melanocytic nevi (nv), and vascular (vasc) skin cancer types, which is one of the most common skin diseases, is important for medical intervention. Otherwise, severe spread, called metastasis, may occur as a result of aggressive growths. For the stated reasons, a deep learning model based on transfer learning, which can classify skin cancer types, has been proposed to assist the medical personnel who serve in this field. With this proposed model, the aim is to classify at high accuracy rates without any pre-processing. As a result of the experimental studies carried out as a result of the stated goals, an accuracy rate of 99,51% was achieved with the proposed model.

Keywords

• Skin cancer
• Deep learning
• CNN
• DenseNet201

Transfer Öğrenme Kullanan Derin Öğrenme Modeli ile Cilt Lezyonlarının Tanımlanması ve Analizi

Öz

Güneş ışıklarından faydalı ışınları olduğu gibi zararlı ışınları da bulunmaktadır. İnsanların çevreye verdikleri zararlar ile oluşan ozon tabakası incelmeleri sonucunda çevresel kirlilik meydana gelmektedir. Bu kirlilikler neticesinde de baş ve boyun gibi doğrudan güneş ışığına maruz kalan bölgelerde cilt hastalıkları görülebilmektedir. En sık olarak görülen cilt hastalıklarından olan actinic keratosis (akiec), basal cell carcinoma (bcc), bening keratosis (bkl), dermafibroma (df), melanoma (mel), melanocytic nevi (nv), ve vascular (vasc) cilt kanseri türlerinin erken aşamada tespit edilmesi tıbbi müdahale açısından önemlidir. Aksi takdirde agresif büyümeler sonucunda metastaz adı verilen şiddetli yayılmalar meydana gelebilmektedir. Belirtilen sebeplerden dolayı bu alanda hizmet veren uzman sağlık personeline yardımcı cilt kanser türlerini sınıflandırabilen transfer öğrenme tabanlı derin öğrenme modeli önerilmiştir. Önerilen bu model ile herhangi bir ön işleme tabi tutmadan yüksek doğruluk oranlarında sınıflandırma yapmak hedeflenmiştir. Belirtilen hedefler sonucunda yapılan deneysel çalışmalar neticesinde önerilen model ile %99.51 oranında başarı oranına ulaşılmıştır.

Anahtar Kelimeler

• Deri kanseri
• Derin öğrenme
• CNN
• DenseNet201

Kaynakça

1. Almansour E., Jaffar MA. Classification of dermoscopic skin cancer images using color and hybrid texture features. IJCSNS Int J Comput Sci Netw Secur 2016; 16(4): 135–139.
2. Anas M., Gupta K., Ahmad S. Skin cancer classification using k-means clustering. International Journal of Technical Research and Applications 2017; 5(1): 62–65.
3. Attique Khan M., Sharif M., Akram T., Kadry S., Hsu C. A two‐stream deep neural network‐based intelligent system for complex skin cancer types classification. International Journal of Intelligent Systems 2021; 1-29.
4. Bakator M., Radosav D. Deep learning and medical diagnosis: a review of literature. Multimodal Technologies and Interaction 2018; 2(3): 1-12.
5. Blum A., Luedtke H., Ellwanger U., Schwabe R., Rassner G., Garbe C. Digital image analysis for diagnosis of cutaneous melanoma. Development of a highly effective computer algorithm based on analysis of 837 melanocytic lesions. British Journal of Dermatology 2004; 151(5): 1029–1038.
6. Çetiner H. Python ortamında derin öğrenme uygulamaları. Anı Yayıncılık, 2021.
7. Chaturvedi SS., Gupta K., Prasad PS. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using MobileNet. International Conference on Advanced Machine Learning Technologies and Applications 2020; 165–176.
8. Cheplygina V., de Bruijne M., Pluim JPW. Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Medical Image Analysis 2019; 54: 280–296.

9. Codella N., Cai J., Abedini M., Garnavi R., Halpern A., Smith JR. Deep learning, sparse coding, and svm for melanoma recognition in dermoscopy images. International Workshop on Machine Learning In Medical Imaging 2015; 118–126.
10. Dorj UO., Lee KK., Choi JY., Lee M. The skin cancer classification using deep convolutional neural network. Multimedia Tools and Applications 2018; 77(8): 9909–9924.
11. Esteva A., Kuprel B., Novoa RA., Ko J., Swetter SM., Blau HM., Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542(7639): 115–118.
12. Giotis I., Molders N., Land S., Biehl M., Jonkman MF., Petkov N. MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Systems with Applications 2015; 42(19): 6578–6585.
13. Goutte C., Gaussier E. A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. Lecture Notes in Computer Science 2005; 345–359.
14. Hosny KM., Kassem MA., Foaud MM. Skin cancer classification using deep learning and transfer learning. 2018 9th Cairo International Biomedical Engineering Conference (CIBEC) 2018; 90–93.
15. Huang G., Liu Z., Van Der Maaten L., Weinberger KQ. Densely connected convolutional networks. Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition 2017; 4700–4708.
16. International Skin Imaging Collaboration. ISIC archive. 2018.
17. Isasi AG., Zapirain BG., Zorrilla AM. Melanomas non-invasive diagnosis application based on the ABCD rule and pattern recognition image processing algorithms. Computers in Biology and Medicine 2011; 41(9): 742–755.
18. Jain S., Singhania U., Tripathy B., Nasr EA., Aboudaif MK., Kamrani AK. Deep learning-based transfer learning for classification of skin cancer. Sensors 2021; 21(23).
19. Kawahara J., Hamarneh G. Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers. International Workshop on Machine Learning in Medical Imaging 2016; 164–171.
20. Krizhevsky A., Sutskever I., Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 2012; 25.
21. Kumar A., Shrestha PR., Pun J., Thapa P., Manandhar M., Sathian B. Profile of skin biopsies and patterns of skin cancer in a tertiary care center of Western Nepal. Asian Pacific Journal of Cancer Prevention 2015; 16(8): 3403–3406.
22. Kwasigroch A, Mikolajczyk A., Grochowski M. Deep neural networks approach to skin lesions classification — A comparative analysis. 2017 22nd International Conference on Methods and Models in Automation and Robotics (MMAR) 2017; 1069–1074.
23. Litjens G., Kooi T., Bejnordi BE., Setio AAA., Ciompi F., Ghafoorian M., Van Der Laak JA., Van Ginneken B., Sánchez CI. A survey on deep learning in medical image analysis. Medical Image Analysis 2017; 42: 60–88.
24. Martens P., McMichael AJ. Environmental change, climate and health: issues and research methods. 2009.
25. McKenzie RL., Björn LO., Bais A., Ilyasd M. Changes in biologically active ultraviolet radiation reaching the Earth’s surface. Photochemical & Photobiological Sciences 2003; 2(1): 5–15.
26. McMichael AJ., McMichael T. Planetary overload: global environmental change and the health of the human species. Cambridge University Press, 1993.
27. Milton MAA. Automated skin lesion classification using ensemble of deep neural networks in ISIC 2018: Skin lesion analysis towards melanoma detection challenge. arXiv preprint, 2019.
28. Moan J., Dahlback A., Porojnicu AC. At what time should one go out in the sun?. Advances in Experimental Medicine and Biology 2008; 624: 86–88.
29. Morid MA., Borjali A., Del Fiol G. A scoping review of transfer learning research on medical image analysis using ImageNet. Computers in Biology and Medicine 2021; 128: 104115.
30. Pacal I., Karaboga D., Basturk A., Akay B., Nalbantoglu U. A comprehensive review of deep learning in colon cancer. Computers in Biology and Medicine 2020; 126: 104003.
31. Perroy R. World population prospects. United Nations 2015; 1(6042): 587–592.
32. Pimentel D., Cooperstein S., Randell H., Filiberto D., Sorrentino S., Kaye B., Nicklin C., Yagi J., Brian J, O’Hern J, Habas A, Weinstein C. Ecology of increasing diseases: population growth and environmental degradation. Human Ecology: An Interdisciplinary Journal 2007; 35(6): 653–668.
33. Pleiss G., Chen D., Huang G., Li T., van der Maaten L., Weinberger KQ. Memory-efficient implementation of DenseNets. arXiv preprint, 2017.
34. Pomponiu V., Nejati H., Cheung NM. Deepmole: Deep neural networks for skin mole lesion classification. 2016 IEEE International Conference on Image Processing (ICIP) 2016; 2623–2627.
35. Ramlakhan K., Shang Y. A mobile automated skin lesion classification system. 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence 2011; 138–141.
36. Rashid J., Ishfaq M., Ghulam A., Saeed MR., Hussain M., Alkhalifah T., Alturise F., Samand N. Skin cancer disease detection using transfer learning technique. Applied Sciences 2022; 12(11): 5714.
37. Ruiz D., Berenguer V., Soriano A., Sánchez B. A decision support system for the diagnosis of melanoma. A comparative approach. Expert Systems with Applications 2011; 38(12): 15217–15223.
38. Shoieb DA., Youssef SM., Aly WM. Computer-aided model for skin diagnosis using deep learning. Journal of Image and Graphics 2016; 4(2): 122–129.
39. Suganyadevi S., Seethalakshmi V., Balasamy K. A review on deep learning in medical image analysis. International Journal of Multimedia Information Retrieval 2022; 11(1): 19–38.
40. Yu X., Zeng N., Liu S., Zhang YD. Utilization of DenseNet201 for diagnosis of breast abnormality. Machine Vision and Applications 2019; 30(7): 1135–1144.